To construct a hybrid decision-making model that integrates knowledge-driven and data-driven approaches, and to apply it to the etiological diagnosis of ventricular tachycardia (VT).

Clinical practice guidelines, expert consensus documents, and medical literature in the field of arrhythmia diseases from 2018 to 2023 were retrieved as knowledge sources. Retrospective electronic medical record data of VT patients from Fuwai Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, from 2013 to 2023 were collected as the dataset. A knowledge-driven model was constructed using a knowledge-rule-based approach to establish clinical pathways. A three-class machine learning model for VT etiology diagnosis was developed based on real-world data, and the best-performing model was selected as the representative of the data-driven approach. The machine learning model was embedded into the decision nodes of the clinical pathway in the form of custom operators, forming the hybrid model. The precision, recall, and F1 score of the three models were evaluated.

Three clinical practice guidelines were included as knowledge sources for the knowledge-driven model. A total of 1305 patient records were collected as the dataset, and five machine learning models were constructed, with the XGBoost model performing the best. The hybrid model adopted a knowledge-driven decision-making framework, embedding the XGBoost model into the decision nodes of a two-level classification. The precision, recall, and F1 scores of the three models were as follows: the knowledge-driven model achieved 80.4%, 79.1%, and 79.7%; the data-driven model achieved 88.4%, 88.5%, and 88.4%; and the hybrid model achieved 90.4%, 90.2%, and 90.3%.

The hybrid model integrating knowledge-driven and data-driven approaches demonstrated higher accuracy, and all its decision outcomes were based on evidence-based practices, aligning more closely with the actual diagnostic reasoning of clinicians. Further rigorous validation is needed to assess the feasibility of widely applying the hybrid model in the medical field.

Cardioneuroablation (CNA) has shown encouraging results in patients with vasovagal syncope (VVS). However, data on different subtypes was scarce.

This observational study retrospectively enrolled 141 patients [mean age: 40 ± 18 years, 51 males (36.2%)] with the diagnosis of VVS. The characteristics among different types of VVS and the outcomes after CNA were analyzed.

After a mean follow-up of 4.3 ± 1.5 years, 41 patients (29.1%) experienced syncope/pre-syncope events after CNA. Syncope/pre-syncope recurrence significantly differed in each subtype (P = 0.04). The cardioinhibitory type of VVS had the lowest recurrence rate after the procedure (n = 6, 16.7%), followed by mixed (n = 26, 30.6%) and vasodepressive (n = 9, 45.0%). Additionally, a significant difference was observed in the analyses of the Kaplan-Meier survival curve (P = 0.02). Syncope/pre-syncope burden was significantly reduced after CNA in the vasodepressive type (P < 0.01). Vasodepressive types with recurrent syncope/pre-syncope after CNA have a lower baseline deceleration capacity (DC) level than those without (7.4 ± 1.0 ms vs. 9.0 ± 1.6 ms, P = 0.01). Patients with DC < 8.4 ms had an 8.1 (HR = 8.1, 95% CI: 2.2–30.0, P = 0.02) times risk of syncope/pre-syncope recurrence after CNA compared to patients with DC ≥ 8.4 ms, and this association still existed after adjusting for age and sex (HR = 8.1, 95% CI: 2.2–30.1, P = 0.02).

Different subtypes exhibit different event-free rates. The vasodepressive type exhibited the lowest event-free rate, but those patients with DC ≥ 8.4 ms might benefit from CNA.

Renal denervation (RDN) is a promising treatment based on catheter intervention for patients with refractory hypertension. However, the effect in patients with isolated systolic hypertension (ISH) remains controversial. The aim of this meta-analysis was to determine the blood pressure lowing effect of RDN in patients with ISH compared with combined systolic/diastolic hypertension (CH) patients.

PubMed, Embase, Cochrane and ClinicalTrials.gov were searched for prospective clinical studies that included RDN. The outcomes of interest were the change of 24-hour ambulatory systolic blood pressure (SBP) from baseline. We used the fixed effects model to calculate weighted mean difference (WMD) with 95% confidence interval (CI).

Six trials were included, with 1405 participants, including 597 patients with ISH and 808 patients with CH. Mean follow-up was five months. The reduction of 24-hour ambulatory SBP was significantly greater for the CH patients than the ISH patients (WMD = 3.89, 95% CI: 2.32–5.45, P < 0.0001). RDN also showed a greater reduction in office SBP in the CH patients compared to the ISH patients (WMD = 10.24, 95% CI: 4.24–15.74, P = 0.0003). And the effect was independent of age, length of follow-up, and ablation device.

RDN provides superior blood pressure control in the CH patients compared with the ISH patients, and the CH patients may be the best suitable population for which RDN is indicated.